Pull global stats, from GDP to CPI.
Claude
ChatGPT
Cursor
Gemini
Windsurf
VS Code
JetBrains
Vercel
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
Knoema MCP connects your AI agent directly to millions of global statistics, including data from sources like the IMF, World Bank, and UN.
You can search for specific economic indicators, retrieve time-series data using mnemonics, and audit metadata on any dataset—all without leaving your chat client.
It's designed for deep dives into macroeconomics, demographics, and environmental trends.
What your AI can do
Search datasets
Finds overall dataset IDs and metadata by searching general terms, helping you identify the correct source for your statistics.
Get dataset metadata
Retrieves detailed background information about a source, helping you understand what variables are actually available.
List data topics
Provides a list of macro categories available in Knoema, like Economy or Demographics, for initial data scoping.
You can search for specific dataset IDs or browse broad categories like 'Economy' or 'Agriculture' using topics and units.
You verify data sources, checking metadata to confirm the exact time period, measurement units (like USD or Percentage), and available regions before running a query.
The agent pulls precise, multi-decade time-series numbers for indicators like GDP or Inflation across multiple countries into one result set.
Ask an AI about this
Compatible AI Apps
OAuth 2.0 CompatibleWaiting for input…
Knoema MCP: 10 Tools for Global Statistics
These tools provide granular control over global data retrieval, allowing you to discover sources, validate units, and pull specific time-series metrics.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Knoema on VinkiusSearch Datasets
Finds overall dataset IDs and metadata by searching general terms, helping you identify the correct source for your statistics.
Get Dataset Metadata
Retrieves detailed background information about a source, helping you understand...
List Data Topics
Provides a list of macro categories available in Knoema, like Economy or...
Get Data Series
Fetches specific historical data points once you know the dataset ID and indicator...
List Dataset Regions
Shows which geographical areas (countries/zones) have data coverage for a specific...
List Data Units
Lists all measurement types, such as Percentage or USD, ensuring your collected figures are comparable.
Get Latest Dataset Data
Pulls the most recently published data points available for any given dataset ID.
Search Data Series
Searches across all available datasets to find highly specific indicators using...
List Data Frequencies
Lists all possible reporting intervals, such as Annual or Quarterly, to help you...
Get Knoema Resource
Accesses generic frontend resources for general data context retrieval.
Connect to your AI in seconds. Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Knoema, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Knoema. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
The sheer volume of global statistics makes research a full-time job.
Today, getting reliable data means opening dozens of institutional websites. You jump between World Bank pages for GDP and the UN site for population metrics. Then you have to copy indicators into Excel, manually checking if every single column uses the same unit (USD vs local currency) or if the date range actually overlaps.
With this MCP, your agent handles that friction entirely. You simply ask: 'Give me 20 years of CPI data for Germany and France.' The system pulls the structured time-series numbers from Knoema's verified sources, giving you a clean, ready-to-use table without any manual cleanup.
Search Data Series: Finding specific indicators across all datasets.
You used to have to know the exact ID of the dataset *and* the indicator name, which is impossible. You’d spend hours wading through metadata just to find out if the data you needed even exists or what its official mnemonic was.
Now, you tell your agent, 'Find me any series related to renewable energy.' The `search_data_series` tool finds it by keyword across millions of records, providing a direct path to the indicator without the manual hunt.
What your AI can actually do with this
Trying to map out global market shifts or forecast resource needs used to be a painful process. You’d open ten tabs, cross-reference data between the World Bank site and an academic journal, manually check units, and spend hours just cleaning up time zones. This MCP changes that. Your agent accesses Knoema's entire catalog of official global statistics.
Instead of wrestling with separate vendor APIs or stale spreadsheets, you simply ask your AI client for what you need—say, the historical CPI change across three countries over 30 years. The system handles the complexity and pulls the structured time-series data directly into your conversation window. When you connect Knoema via Vinkius, your agent gains immediate access to global data depth, letting you focus on analysis instead of aggregation.
019d75c2-18e0-72b6-b9fc-cc15c735185a Here's how it actually works
The bottom line is that you ask a question in plain English, and the MCP handles all the complex database calls needed to answer it with verifiable statistics.
First, connect your AI client and enter your Knoema Client ID and Secret. This authenticates the connection to the service.
Next, ask your agent a natural language question—for instance, 'What were the oil prices in 2015?' The agent then translates this into structured calls using tools like search_data_series.
Finally, you get back the required data payload. The results appear formatted and ready for immediate analysis within your chat client.
Who is this actually for?
This MCP is for people who need data depth, not just quick numbers. If your job involves comparing global trends or modeling macro risk, you need this. It's built for the user who gets impatient staring at a dashboard that only shows last quarter’s performance.
You compare historical inflation rates and currency movements across different economic blocs to model portfolio risk.
You pull demographic data alongside sector-specific indicators to identify emerging consumer markets in specific global regions.
You fetch multiple time-series datasets, like GDP and renewable energy capacity, to train forecasting models for academic studies.
What Changes When You Connect
You don't waste time comparing dozens of individual vendor sites. By using search_data_series, your agent finds a specific indicator like 'Crude Oil Price' across multiple providers in one search.
Stop guessing if the data is comparable. Before fetching numbers, you use get_dataset_metadata to audit the source, confirming details like whether the unit is USD or EUR and what country codes are used.
Forget scraping websites for the latest numbers. The get_latest_dataset_data tool pulls the most recent official reports directly into your conversation window when you need current context.
The MCP helps narrow down global scope efficiently. If you only care about North America, you use list_dataset_regions first, ensuring all subsequent calls are limited to relevant geography.
You can quickly understand what data is available without knowing the source name. Use search_datasets and list_data_topics together to scope your research by subject matter (e.g., 'Energy' or 'Health').
The MCP lets you confirm if a dataset supports Annual, Quarterly, or Monthly reporting via list_data_frequencies, ensuring your time-series analysis is based on consistent data cadence.
See it in action
Modeling Cross-Sectoral Economic Stress
A financial analyst needs to compare US unemployment rates against EU inflation over the last decade. They use search_data_series to find both indicators, then run get_data_series multiple times, getting a unified view for their risk model.
Planning Infrastructure Expansion
A corporate strategist must assess the market potential in Southeast Asia. They use list_data_topics to narrow down demographics and then query search_datasets to find relevant population growth stats for target regions.
Academic Research on Climate Impact
A researcher needs environmental metrics. They first list available data units (list_data_units) to ensure they are comparing tons of CO2 emissions versus percentage changes before retrieving the actual time-series figures.
Competitive Analysis for New Markets
A business planner needs current market indicators. They use get_latest_dataset_data combined with list_dataset_regions to pull real-time metrics on specific commodities across their target countries.
The honest tradeoffs
Relying only on Google search
The user searches 'global gdp data' and gets a list of ten different government reports, forcing them to manually check which one is the most current or comprehensive.
Instead, ask your agent to use search_datasets first. This surfaces all potential sources in one place. Then, use get_dataset_metadata on the best candidate to verify its scope before pulling data.
Assuming standardized metrics
The user pulls two sets of numbers for 'Inflation' but gets confused because one dataset reports it as a percentage change while the other uses an index number.
Always check your parameters. Before getting data, run list_data_units and use the resulting unit type in conjunction with get_dataset_metadata to confirm consistency across all fields.
Overlooking data granularity
The user tries to find a specific indicator like 'China's solar panel output', but their initial search fails because they didn't know the exact technical name (mnemonic).
Don't guess. Use search_data_series. It searches by keyword across all datasets and is far more granular than simply searching for a dataset ID.
When It Fits, When It Doesn't
Use this MCP if your work requires macro-level, historical, or global economic data—think decades of GDP comparisons or environmental trend mapping. You need the depth that comes from sources like IMF and World Bank. Don't use it if you need real-time stock ticks, proprietary internal company metrics, or highly localized sensor feeds (like IoT). For those cases, your agent needs a different type of connector. If your only requirement is to find basic demographic information without time series context, then using list_data_topics might be enough; but if you need the numbers, stick with this MCP's core tools.
Questions you might have
How do I find what data topics are available using list_data_topics? +
You run list_data_topics, and it gives you a structured list of high-level categories, like 'Agriculture' or 'Economy'. This helps scope your search before committing to specific indicators.
What is the difference between search_datasets and search_data_series? +
search_datasets finds the overall source (the container), giving you metadata. search_data_series, however, searches inside all sources to find a specific indicator by keyword.
I need data for 196 countries; should I use list_dataset_regions? +
Yes, running list_dataset_regions confirms which geographical areas are covered by the dataset you're looking at. This prevents your agent from querying a source that only covers North America.
How do I confirm if data is available monthly or quarterly? +
Use list_data_frequencies. It shows all valid time intervals (Annual, Quarterly, Monthly), letting you set the correct scope for your time-series query.
How do I use `get_dataset_metadata` to check which variables a dataset contains? +
It returns the full structure of the data, telling you exactly what variables are available. This is crucial because it lets you confirm all fields and units before attempting to retrieve any values using other tools.
If I use `get_data_series` with incorrect mnemonics, how does the system handle the error? +
The agent reports a specific validation failure. You'll receive an error message detailing exactly which mnemonic failed and why it couldn't be found in the Knoema catalog.
Does `get_latest_dataset_data` provide better performance than using `get_data_series`? +
Yes, it is optimized for speed by fetching only the most recent data points. This saves time and reduces payload size when you just need a quick snapshot of current trends.
Where can I find out what measurement types are supported using `list_data_units`? +
It provides a comprehensive list of all available units, like USD or percentage. This is useful because it ensures your analysis is correct and you know exactly how the raw figures are measured.
Where do I get my Knoema API credentials? +
Visit the Knoema Developer Portal (knoema.com/dev), create an application, and you will receive a Client ID and Client Secret.
How can I find a specific dataset ID? +
Use the search_datasets tool with relevant keywords. The tool will return a list of matching datasets along with their unique IDs.
What is a mnemonic in Knoema? +
A mnemonic is a short, human-readable code used to identify a specific data series within a dataset (e.g., 'NGDP' for Nominal GDP).
We've already built the connector for Knoema. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.